Large Language Model
CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes Y ulei Qin 1 Xingyu Chen
For instance, web images retrieved with queries of " tiger cat " (a cat species) and " drumstick " (a musical instrument) are almost dominated by images of tigers and
Im-Promptu: In-Context Composition from Image Prompts
In this work, we investigate whether analogical reasoning can enable in-context composition over composable elements of visual stimuli.
Fine-Tuning Language Models with Just Forward Passes Sadhika Malladi Tianyu Gao
In this work, we propose a memory-efficient zeroth-order optimizer ( MeZO), adapting the classical ZO-SGD method to operate in-place, thereby fine-tuning LMs with the same memory footprint as inference .
SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs Supplementary Materials Appendix Overview
Appendix B provides additional implementation details, including a video SP AE variant. Appendix C includes more quantitative evaluation results. Appendix D shows more qualitative examples of model generations. Figure 1 shows an example of the dilation subsampler defined by Eq. (1). We select evenly distributed positions in each layer to form the token pyramid with monotonically increasing layer sizes.
Benchmarking Large Language Models on CMExam - A Comprehensive Chinese Medical Exam Dataset
The results show that GPT -4 had the best accuracy of 61.6% and a weighted F1
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
Large language models(LLMs) have sparked a new wave of exciting AI applications. Hosting these models at scale requires significant memory resources.
Overleaf Example
Baseline Methods As standard baselines, we first consider zero-shot CLIP (ZS) and vanilla fine-tuning (FT) with contrastive loss. We construct the label map for contrastive loss by regarding all of the samples from a class as positives. A.3 Multi-modal Classification Dataset To evaluate the multi-modal representation learning under video emotional classification, CMU-MOSEI consists of three modalities textual (T), visual (V), and audio (A), and contains 23,453 Y ouTube video clips about diverse movie reviews, and each clip is annotated with ordinal labels ranging from -3 (strong negative) to 3 (strong positive). While MulT learns the joint encoder only with standard classification loss (i.e., cross-entropy loss; Metric For image-text retrieval, we adopt top-1 and top-5 recalls likewise CLIP retrieval setup. Flickr30k for zero-shot transferred image-text retrieval.
A Cooperative Role Playing The Good Mind
For each (topic, subtopic) pair, we generate and solve 80 problems using GPT4.